The paper lists “avoiding reward hacking” as one of five practical research problems on accident risk, with “avoiding side effects”.

The exact words it rests on

We present a list of five practical research problems related to accident risk, categorized according to whether the problem originates from having the wrong objective function ("avoiding side effects" and "avoiding reward hacking"), an objective function that is too expensive to evaluate frequently ("scalable supervision"), or undesirable behavior during the learning process ("safe exploration" and "distributional shift").

What the source said when we opened it, on 13 Oct 2026.

The source

Concrete Problems in AI Safety (arXiv 1606.06565)
arXiv · 2016-06-21

Open the sourcearchived copy

Checked

Checked by the notis newsroom on 13 Oct 2026, against the source above.

In the story

Dario Amodei wants outside testers inside frontier AI companies 14 Oct 2026